Future failure rate prediction for switchgears in power systems

• Main Author: Huang, Siqi
• Other Authors: Hu, Guoqiang
• Format: Thesis-Master by Coursework
• Language: English
• Published: Nanyang Technological University 2021
• Subjects: Engineering::Electrical and electronic engineering
• Online Access: https://hdl.handle.net/10356/150741
• Institution: Nanyang Technological University

Switchgear is an essential piece of equipment in the distribution network, and its normal operation plays a critical role in the safety and stability of the power system. Although many studies have focused on switchgear's failure analysis, most of them either only study the classification of failures and ignore the prediction or make predictions based on sufficient historical fault characteristic value data. This project uses a classification and prediction systematic pipeline, focusing on both failure type classification and future failure rate prediction. An encoder-decoder neural network is proposed to achieve accurate and robust failure rate prediction of different switchgear partial discharge defects. Simulation results show that our approach significantly outperforms baseline methods on the simulated switchgear characteristic dataset.